Unlock instant, AI-driven research and patent intelligence for your innovation.

Template Matching Tracking Method for Moving Target

A template matching and moving target technology, applied in character and pattern recognition, image analysis, instruments, etc., can solve the problems of tracking failure, inability to locate the target position correctly, low tracking performance, etc., and achieve the effect of improving adaptability

Active Publication Date: 2022-03-04
SHENYANG LIGONG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, when the target has a certain tilt or rotation, it often leads to the inability to correctly locate the target position, resulting in tracking failure
In addition, this method is also very sensitive to illumination changes, and the tracking performance is not high.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Template Matching Tracking Method for Moving Target
  • Template Matching Tracking Method for Moving Target
  • Template Matching Tracking Method for Moving Target

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The present invention will be further described in detail below with reference to the examples and drawings.

[0013] The present invention uses a template matching method to realize the identification and tracking of the target. Set the pixel gradation value of the position in the template image A (i, j) is a i,j 8 adjacent pixel gradation values ​​around it is {a i-1,j , A i+1,j , A i,j-1 , A i,j+1 , A i-1,j-1 , A i+1,j+1 , A i-1,j+1 , A i+1,j-1 }, Thus available (i, j) position pixels gray neighborhood difference B i,j for:

[0014]

[0015] Thereby, the gradation of the template image A can be obtained respectively, respectively, the difference between the gradation, where the template grayscale (X a Y a ) Can be calculated as:

[0016]

[0017]

[0018] Where X a Gray Cathoric Space for Template A Image A, Y a The gradation centric ordinate of the template image A. Similarly, template grayscale neighborhood difference quality (X b Y b ) Can be calculated as:

[0...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the field of image processing and machine vision, in particular to a template matching and tracking method for a moving target. Calculate the gray-scale centroid and gray-scale neighborhood difference centroid of the template and the area to be matched, and determine the connection line between the center and the gray-scale centroid and the connection line between the center and the gray-scale neighborhood difference centroid as the gray-scale reference direction and gray-scale Neighborhood difference reference direction, coincide the template with the center of the area to be matched, the gray reference direction and the gray neighbor difference reference direction, calculate the matching criterion function value, determine the best matching position as the target position, and according to the matching The weighting coefficients are updated as a result, which improves the adaptability of the tracking method to changes in rotation. The invention can be used in target recognition and tracking system.

Description

Technical field [0001] The present invention belongs to the field of image processing and the machine visual field, involving a target identification and tracking method, and more particularly to a target identification and tracking method (template matching tracking method) based on template matching method (template matching tracking method). Background technique [0002] The identification and tracking of the target has always been important research content in the field of machine vision and image processing. There is an important value in the fields of national defense military, intelligent transportation, video surveillance. Target identification and tracking systems typically have strict requirements for the real-time performance of the tracking method, so a simple and reliable tracking method has good application prospects. For example, when the tracking scenario is simple, a "double-wave door" method can be employed, which distinguishes the target and background image by...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/246G06T7/66G06T7/73G06V10/75
CPCG06V20/42G06F18/22
Inventor 孟博
Owner SHENYANG LIGONG UNIV